© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35446
    Prev
    Next
    INDEX
    Explanations

    exclamations and thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹Ĵä¹ĵ
    -0.09
    æ²ī
    -0.08
     Erot
    -0.08
    çĩĥ
    -0.08
    å¾ĹçŁ¥
    -0.08
    ä¹Łæľīå¾Īå¤ļ
    -0.08
    ãħ¤
    -0.08
    è¯įæĿ¡
    -0.07
    ured
    -0.07
    èĩªçIJĨ
    -0.07
    POSITIVE LOGITS
    ä¸ĩåĪĨ
    0.09
     Vox
    0.09
    .break
    0.09
    åľ°ä¸Ń
    0.08
    åģļå®Į
    0.08
    éľ¾
    0.08
    gos
    0.08
    åģ¥åº·çļĦ
    0.08
    abet
    0.08
    éĵį
    0.08
    Activations Density 0.121%

    No Known Activations